Yes, it's not surprising that warnings and complexity increased at a higher rate when paired with increased velocity. Increased velocity == increased lines of code.
Does the study normalize velocity between the groups by adjusting the timeframes so that we could tell if complexity and warnings increased at a greater rate per line of code added in the AI group?
I suspect it would, since I've had to simplify AI generated code on several occasions but right now the study just seems to say that the larger a code base grows the more complex it gets which is obvious.
AstroBen 1 hours ago [-]
"Notably, increases in codebase size are a major determinant of increases in static analysis warnings and code complexity, and absorb most variance in the two outcome variables. However, even with strong controls for codebase size dynamics, the adoption of Cursor still has a significant effect on code complexity, leading to a 9% baseline increase on average compared to projects in similar dynamics but not using Cursor."
ex-aws-dude 2 hours ago [-]
That was my thought as well, because obviously complexity increases when a project grows regardless of AI
2 hours ago [-]
bensyverson 2 hours ago [-]
Yeah, I have a more complex project I'm working on with Claude, but it's not that Claude is making it more complex; it's just that it's so complex I wouldn't attempt it without Claude.
rfw300 2 hours ago [-]
Super interesting study. One curious thing I've noticed is that coding agents tend to increase the code complexity of a project, but simultaneously massively reduce the cost of that code complexity.
If a module becomes unsustainably complex, I can ask Claude questions about it, have it write tests and scripts that empirically demonstrate the code's behavior, and worse comes to worst, rip out that code entirely and replace it with something better in a fraction of the time it used to take.
That's not to say complexity isn't bad anymore—the paper's findings on diminishing returns on velocity seem well-grounded and plausible. But while the newest (post-Nov. 2025) models often make inadvisable design decisions, they rarely do things that are outright wrong or hallucinated anymore. That makes them much more useful for cleaning up old messes.
joshribakoff 2 hours ago [-]
Bad code has real world consequences. Its not limited to having to rewrite it. The cost might also include sanctions, lost users, attrition, and other negative consequences you don’t just measure in dev hours
SR2Z 2 hours ago [-]
Right, but that cost is also incurred by human-written code that happens to have bugs.
In theory experienced humans introduce less bugs. That sounds reasonable and believable, but anyone who's ever been paid to write software knows that finding reliable humans is not an easy task unless you're at a large established company.
MeetingsBrowser 2 hours ago [-]
The question then becomes, can LLMs generate code close to the same quality as professionals.
In my experience, they are not even close.
mathgeek 42 minutes ago [-]
We should qualify that kind of statement, as it’s valuable to define just what percentile of “professional developers” the quality falls into. It will likely never replace p90 developers for example, but it’s better than somewhere between there and p10. Arbitrary numbers for examples.
MeetingsBrowser 2 minutes ago [-]
Can you quantify the quality of a p90 or p10 developer?
I would frame it differently. There are developers successfully shipping product X. Those developer are, on average, as skilled as necessary to work on project X. else they would have moved on or the project would have failed.
Can LLMs produce the same level of quality as project X developers? The only projects I know of where this is true are toy and hobby projects.
verdverm 2 hours ago [-]
There was a recent study posted here that showed AI introduces regressions at an alarming rate, all but one above 50%, which indicates they spend a lot of time fixing their own mistakes. You've probably seen them doing this kind of thing, making one change that breaks another, going and adjusting that thing, not realizing that's making things worse.
2 hours ago [-]
MeetingsBrowser 2 hours ago [-]
This only helps if you notice the code is bad. Especially in overlay complex code, you have to really be paying attention to notice when a subtle invariant is broken, edge case missed, etc.
Its the same reason a junior + senior engineer is about as fast as a senior + 100 junior engineers. The senior's review time becomes the bottleneck and does not scale.
And even with the latest models and tooling, the quality of the code is below what I expect from a junior. But you sure can get it fast.
AlexandrB 11 minutes ago [-]
> Super interesting study. One curious thing I've noticed is that coding agents tend to increase the code complexity of a project, but simultaneously massively reduce the cost of that code complexity.
This is the same pattern I observed with IDEs. Autocomplete and being able to jump to a definition means spaghetti code can be successfully navigated so there's no "natural" barrier to writing spaghetti code.
i_love_retros 24 minutes ago [-]
> have it write tests
Just make sure it hasn't mocked so many things that nothing is actually being tested. Which I've witnessed.
moregrist 2 minutes ago [-]
I’ve also seen Opus 4.5 and 4.6 churn out tons of essentially meaningless tests, including ones where it sets a field on a structure and then tests that the field was set.
You have to actually care about quality with these power saws or you end up with poorly-fitting cabinets and might even lose a thumb in the process.
mentalgear 59 minutes ago [-]
> We find that the adoption of Cursor leads to a statistically significant, large, but transient increase in project-level development velocity, along with a substantial and persistent increase in static analysis warnings and code complexity. Further panel generalized-method-of-moments estimation reveals that increases in static analysis warnings and code complexity are major factors driving long-term velocity slowdown. Our study identifies quality assurance as a major bottleneck for early Cursor adopters and calls for it to be a first-class citizen in the design of agentic AI coding tools and AI-driven workflows.
So overall seems like the pros and cons of "AI vibe coding" just cancel themselves out.
dalemhurley 36 minutes ago [-]
I think the issue is people AI assisted code, test then commit.
Traditional software dev would be build, test, refactor, commit.
Even the Clean Coder recommends starting with messy code then tidying it up.
We just need to apply traditional methods to AI assisted coding.
duendefm 12 minutes ago [-]
AI is not perfect sure, one has to know how to use it. But this study is already flawed since models improved a lot since the beginning of 2026.
2 hours ago [-]
AstroBen 2 hours ago [-]
They're measuring development speed through lines of code. To show that's true they'd need to first show that AI and humans use the same number of lines to solve the same problem. That hasn't been my experience at all. AI is incredibly verbose.
Then there's the question of if LoC is a reliable proxy for velocity at all? The common belief amongst developers is that it's not.
2 hours ago [-]
PeterStuer 2 hours ago [-]
Interesting from an historical perspective. But data from 4/2025? Might as well have been last century.
happycube 2 hours ago [-]
I think the gist of it still applies to even Claude Code w/Opus 4.6.
It's basically outsourcing to mediocre programmers - albeit very fast ones with near-infinite patience and little to no ego.
Miraste 2 hours ago [-]
It doesn't map well to a mediocre human programmer, I think. It operates in a much more jagged world between superhuman, and inhuman stupidity.
1 hours ago [-]
chris_money202 55 minutes ago [-]
Now someone do a research study where a summary of this research paper is in the AGENTS.md and let’s see if the overall outcomes are better
mellosouls 1 hours ago [-]
Depends on the nature of the tool I would imagine - eg. Claude Code Terminal (say) would have higher entry requirements in terms of engineering experience (Cursor was sold as newbie-friendly) so I would predict higher quality code than Cursor in a similar survey.
ofc that doesn't take into account the useful high-level and other advantages of IDEs that might mitigate against slop during review, but overall Cursor was a more natural fit for vibe-coders.
This is said without judgement - I was a cheerleader for Cursor early on until it became uncompetitive in value.
productinventor 21 minutes ago [-]
[flagged]
scka-de 1 hours ago [-]
[dead]
ryguz 2 hours ago [-]
[dead]
simumw 2 hours ago [-]
[flagged]
rkomorn 2 hours ago [-]
I hope this is just an edit away from making more sense to me.
2 hours ago [-]
Rendered at 20:00:24 GMT+0000 (Coordinated Universal Time) with Vercel.
Does the study normalize velocity between the groups by adjusting the timeframes so that we could tell if complexity and warnings increased at a greater rate per line of code added in the AI group?
I suspect it would, since I've had to simplify AI generated code on several occasions but right now the study just seems to say that the larger a code base grows the more complex it gets which is obvious.
If a module becomes unsustainably complex, I can ask Claude questions about it, have it write tests and scripts that empirically demonstrate the code's behavior, and worse comes to worst, rip out that code entirely and replace it with something better in a fraction of the time it used to take.
That's not to say complexity isn't bad anymore—the paper's findings on diminishing returns on velocity seem well-grounded and plausible. But while the newest (post-Nov. 2025) models often make inadvisable design decisions, they rarely do things that are outright wrong or hallucinated anymore. That makes them much more useful for cleaning up old messes.
In theory experienced humans introduce less bugs. That sounds reasonable and believable, but anyone who's ever been paid to write software knows that finding reliable humans is not an easy task unless you're at a large established company.
In my experience, they are not even close.
I would frame it differently. There are developers successfully shipping product X. Those developer are, on average, as skilled as necessary to work on project X. else they would have moved on or the project would have failed.
Can LLMs produce the same level of quality as project X developers? The only projects I know of where this is true are toy and hobby projects.
Its the same reason a junior + senior engineer is about as fast as a senior + 100 junior engineers. The senior's review time becomes the bottleneck and does not scale.
And even with the latest models and tooling, the quality of the code is below what I expect from a junior. But you sure can get it fast.
This is the same pattern I observed with IDEs. Autocomplete and being able to jump to a definition means spaghetti code can be successfully navigated so there's no "natural" barrier to writing spaghetti code.
Just make sure it hasn't mocked so many things that nothing is actually being tested. Which I've witnessed.
You have to actually care about quality with these power saws or you end up with poorly-fitting cabinets and might even lose a thumb in the process.
So overall seems like the pros and cons of "AI vibe coding" just cancel themselves out.
Traditional software dev would be build, test, refactor, commit.
Even the Clean Coder recommends starting with messy code then tidying it up.
We just need to apply traditional methods to AI assisted coding.
Then there's the question of if LoC is a reliable proxy for velocity at all? The common belief amongst developers is that it's not.
It's basically outsourcing to mediocre programmers - albeit very fast ones with near-infinite patience and little to no ego.
ofc that doesn't take into account the useful high-level and other advantages of IDEs that might mitigate against slop during review, but overall Cursor was a more natural fit for vibe-coders.
This is said without judgement - I was a cheerleader for Cursor early on until it became uncompetitive in value.